© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39588
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    immel
    -0.07
    utron
    -0.06
    iggs
    -0.06
    izard
    -0.06
    essim
    -0.06
     Libraries
    -0.06
    995
    -0.06
    EventListener
    -0.05
    utting
    -0.05
    绩
    -0.05
    POSITIVE LOGITS
    duÄŁ
    0.07
    ISK
    0.06
    oldur
    0.06
    hled
    0.06
     Downs
    0.06
    _CTL
    0.06
    jab
    0.06
     ("-
    0.06
     encour
    0.06
    INK
    0.06
    Activations Density 0.005%

    No Known Activations